From 2c51950e7340888e010a48b9408732accdbfdfe1 Mon Sep 17 00:00:00 2001
From: yuanmengqi <yuanmengqi@mail.ustc.edu.cn>
Date: Thu, 17 Jul 2025 10:50:10 +0000
Subject: [PATCH] feat: enhance evaluator configuration for Chrome with
 post-execution commands

- Added postconfig commands to multiple JSON files for Chrome evaluation examples.
- Included commands to terminate existing Chrome processes, launch Chrome with remote debugging, and introduce sleep intervals for timing.
- Updated logging messages in the AWS manager to improve clarity and user experience.

These changes enhance the automation and usability of the evaluation examples while preserving existing logic.
---
 desktop_env/providers/aws/manager.py          |  5 +-
 .../030eeff7-b492-4218-b312-701ec99ee0cc.json | 26 ++++++++++
 .../2ad9387a-65d8-4e33-ad5b-7580065a27ca.json | 26 ++++++++++
 .../2ae9ba84-3a0d-4d4c-8338-3a1478dc5fe3.json |  6 +++
 .../44ee5668-ecd5-4366-a6ce-c1c9b8d4e938.json |  6 +++
 .../480bcfea-d68f-4aaa-a0a9-2589ef319381.json |  6 +++
 .../7a5a7856-f1b6-42a4-ade9-1ca81ca0f263.json | 26 ++++++++++
 .../7b6c7e24-c58a-49fc-a5bb-d57b80e5b4c3.json | 26 ++++++++++
 .../9656a811-9b5b-4ddf-99c7-5117bcef0626.json | 23 ++++++--
 .../99146c54-4f37-4ab8-9327-5f3291665e1e.json | 23 ++++++--
 .../af630914-714e-4a24-a7bb-f9af687d3b91.json |  6 +++
 .../bb5e4c0d-f964-439c-97b6-bdb9747de3f4.json | 52 +------------------
 12 files changed, 172 insertions(+), 59 deletions(-)

diff --git a/desktop_env/providers/aws/manager.py b/desktop_env/providers/aws/manager.py
index 2d80380..703359b 100644
--- a/desktop_env/providers/aws/manager.py
+++ b/desktop_env/providers/aws/manager.py
@@ -128,7 +128,6 @@ def _allocate_vm(region=DEFAULT_REGION, screen_size=(1920, 1080)):
         waiter.wait(InstanceIds=[instance_id])
         logger.info(f"Instance {instance_id} is ready.")
         
-        # 获取并显示VNC访问地址
         try:
             instance_details = ec2_client.describe_instances(InstanceIds=[instance_id])
             instance = instance_details['Reservations'][0]['Instances'][0]
@@ -140,8 +139,8 @@ def _allocate_vm(region=DEFAULT_REGION, screen_size=(1920, 1080)):
                 logger.info(f"📡 Public IP: {public_ip}")
                 logger.info(f"🆔 Instance ID: {instance_id}")
                 logger.info("="*80)
-                print(f"\n🌐 VNC访问地址: {vnc_url}")
-                print(f"📍 请在浏览器中打开上述地址进行远程桌面访问\n")
+                print(f"\n🌐 VNC Web Access URL: {vnc_url}")
+                print(f"📍 Please open the above address in the browser for remote desktop access\n")
         except Exception as e:
             logger.warning(f"Failed to get VNC address for instance {instance_id}: {e}")
     except KeyboardInterrupt:
diff --git a/evaluation_examples/examples/chrome/030eeff7-b492-4218-b312-701ec99ee0cc.json b/evaluation_examples/examples/chrome/030eeff7-b492-4218-b312-701ec99ee0cc.json
index 4f9726c..c7114ce 100644
--- a/evaluation_examples/examples/chrome/030eeff7-b492-4218-b312-701ec99ee0cc.json
+++ b/evaluation_examples/examples/chrome/030eeff7-b492-4218-b312-701ec99ee0cc.json
@@ -29,6 +29,32 @@
     "chrome"
   ],
   "evaluator": {
+    "postconfig": [
+      {
+        "type": "launch",
+        "parameters": {
+          "command": [
+            "pkill",
+            "chrome"
+          ]
+        }
+      },
+      {
+        "type": "launch",
+        "parameters": {
+          "command": [
+            "google-chrome",
+            "--remote-debugging-port=1337"
+          ]
+        }
+      },
+      {
+        "type": "sleep",
+        "parameters": {
+          "seconds": 3
+        }
+      }
+    ],
     "func": "exact_match",
     "result": {
       "type": "enable_do_not_track"
diff --git a/evaluation_examples/examples/chrome/2ad9387a-65d8-4e33-ad5b-7580065a27ca.json b/evaluation_examples/examples/chrome/2ad9387a-65d8-4e33-ad5b-7580065a27ca.json
index 48a0113..ef753d6 100644
--- a/evaluation_examples/examples/chrome/2ad9387a-65d8-4e33-ad5b-7580065a27ca.json
+++ b/evaluation_examples/examples/chrome/2ad9387a-65d8-4e33-ad5b-7580065a27ca.json
@@ -29,6 +29,32 @@
     "chrome"
   ],
   "evaluator": {
+    "postconfig": [
+      {
+        "type": "launch",
+        "parameters": {
+          "command": [
+            "pkill",
+            "chrome"
+          ]
+        }
+      },
+      {
+        "type": "launch",
+        "parameters": {
+          "command": [
+            "google-chrome",
+            "--remote-debugging-port=1337"
+          ]
+        }
+      },
+      {
+        "type": "sleep",
+        "parameters": {
+          "seconds": 3
+        }
+      }
+    ],
     "func": "is_expected_bookmarks",
     "result": {
       "type": "bookmarks"
diff --git a/evaluation_examples/examples/chrome/2ae9ba84-3a0d-4d4c-8338-3a1478dc5fe3.json b/evaluation_examples/examples/chrome/2ae9ba84-3a0d-4d4c-8338-3a1478dc5fe3.json
index c3d0677..14404dd 100644
--- a/evaluation_examples/examples/chrome/2ae9ba84-3a0d-4d4c-8338-3a1478dc5fe3.json
+++ b/evaluation_examples/examples/chrome/2ae9ba84-3a0d-4d4c-8338-3a1478dc5fe3.json
@@ -47,6 +47,12 @@
             "--remote-debugging-port=1337"
           ]
         }
+      },
+      {
+        "type": "sleep",
+        "parameters": {
+          "seconds": 3
+        }
       }
     ],
     "func": "exact_match",
diff --git a/evaluation_examples/examples/chrome/44ee5668-ecd5-4366-a6ce-c1c9b8d4e938.json b/evaluation_examples/examples/chrome/44ee5668-ecd5-4366-a6ce-c1c9b8d4e938.json
index b49f40d..39c59f0 100644
--- a/evaluation_examples/examples/chrome/44ee5668-ecd5-4366-a6ce-c1c9b8d4e938.json
+++ b/evaluation_examples/examples/chrome/44ee5668-ecd5-4366-a6ce-c1c9b8d4e938.json
@@ -254,6 +254,12 @@
             "--remote-debugging-port=1337"
           ]
         }
+      },
+      {
+        "type": "sleep",
+        "parameters": {
+          "seconds": 3
+        }
       }
     ],
     "func": "check_history_deleted",
diff --git a/evaluation_examples/examples/chrome/480bcfea-d68f-4aaa-a0a9-2589ef319381.json b/evaluation_examples/examples/chrome/480bcfea-d68f-4aaa-a0a9-2589ef319381.json
index 5a9b16e..4ac32ab 100644
--- a/evaluation_examples/examples/chrome/480bcfea-d68f-4aaa-a0a9-2589ef319381.json
+++ b/evaluation_examples/examples/chrome/480bcfea-d68f-4aaa-a0a9-2589ef319381.json
@@ -47,6 +47,12 @@
             "--remote-debugging-port=1337"
           ]
         }
+      },
+      {
+        "type": "sleep",
+        "parameters": {
+          "seconds": 3
+        }
       }
     ],
     "func": "check_enabled_experiments",
diff --git a/evaluation_examples/examples/chrome/7a5a7856-f1b6-42a4-ade9-1ca81ca0f263.json b/evaluation_examples/examples/chrome/7a5a7856-f1b6-42a4-ade9-1ca81ca0f263.json
index 49f1cc3..e5f3f17 100644
--- a/evaluation_examples/examples/chrome/7a5a7856-f1b6-42a4-ade9-1ca81ca0f263.json
+++ b/evaluation_examples/examples/chrome/7a5a7856-f1b6-42a4-ade9-1ca81ca0f263.json
@@ -38,6 +38,32 @@
     "chrome"
   ],
   "evaluator": {
+    "postconfig": [
+      {
+        "type": "launch",
+        "parameters": {
+          "command": [
+            "pkill",
+            "chrome"
+          ]
+        }
+      },
+      {
+        "type": "launch",
+        "parameters": {
+          "command": [
+            "google-chrome",
+            "--remote-debugging-port=1337"
+          ]
+        }
+      },
+      {
+        "type": "sleep",
+        "parameters": {
+          "seconds": 3
+        }
+      }
+    ],
     "func": "is_expected_bookmarks",
     "result": {
       "type": "bookmarks"
diff --git a/evaluation_examples/examples/chrome/7b6c7e24-c58a-49fc-a5bb-d57b80e5b4c3.json b/evaluation_examples/examples/chrome/7b6c7e24-c58a-49fc-a5bb-d57b80e5b4c3.json
index 610b3ba..d8b0428 100644
--- a/evaluation_examples/examples/chrome/7b6c7e24-c58a-49fc-a5bb-d57b80e5b4c3.json
+++ b/evaluation_examples/examples/chrome/7b6c7e24-c58a-49fc-a5bb-d57b80e5b4c3.json
@@ -38,6 +38,32 @@
     "chrome"
   ],
   "evaluator": {
+    "postconfig": [
+      {
+        "type": "launch",
+        "parameters": {
+          "command": [
+            "pkill",
+            "chrome"
+          ]
+        }
+      },
+      {
+        "type": "launch",
+        "parameters": {
+          "command": [
+            "google-chrome",
+            "--remote-debugging-port=1337"
+          ]
+        }
+      },
+      {
+        "type": "sleep",
+        "parameters": {
+          "seconds": 3
+        }
+      }
+    ],
     "func": "is_cookie_deleted",
     "result": {
       "type": "cookie_data",
diff --git a/evaluation_examples/examples/chrome/9656a811-9b5b-4ddf-99c7-5117bcef0626.json b/evaluation_examples/examples/chrome/9656a811-9b5b-4ddf-99c7-5117bcef0626.json
index e0e9d1a..1db5215 100644
--- a/evaluation_examples/examples/chrome/9656a811-9b5b-4ddf-99c7-5117bcef0626.json
+++ b/evaluation_examples/examples/chrome/9656a811-9b5b-4ddf-99c7-5117bcef0626.json
@@ -31,10 +31,27 @@
   "evaluator": {
     "postconfig": [
       {
-        "type": "execute",
+        "type": "launch",
         "parameters": {
-          "command": "pkill chrome",
-          "shell": "true"
+          "command": [
+            "pkill",
+            "chrome"
+          ]
+        }
+      },
+      {
+        "type": "launch",
+        "parameters": {
+          "command": [
+            "google-chrome",
+            "--remote-debugging-port=1337"
+          ]
+        }
+      },
+      {
+        "type": "sleep",
+        "parameters": {
+          "seconds": 3
         }
       }
     ],
diff --git a/evaluation_examples/examples/chrome/99146c54-4f37-4ab8-9327-5f3291665e1e.json b/evaluation_examples/examples/chrome/99146c54-4f37-4ab8-9327-5f3291665e1e.json
index 11a8bc2..ca61400 100644
--- a/evaluation_examples/examples/chrome/99146c54-4f37-4ab8-9327-5f3291665e1e.json
+++ b/evaluation_examples/examples/chrome/99146c54-4f37-4ab8-9327-5f3291665e1e.json
@@ -31,10 +31,27 @@
   "evaluator": {
     "postconfig": [
       {
-        "type": "execute",
+        "type": "launch",
         "parameters": {
-          "command": "pkill chrome",
-          "shell": "true"
+          "command": [
+            "pkill",
+            "chrome"
+          ]
+        }
+      },
+      {
+        "type": "launch",
+        "parameters": {
+          "command": [
+            "google-chrome",
+            "--remote-debugging-port=1337"
+          ]
+        }
+      },
+      {
+        "type": "sleep",
+        "parameters": {
+          "seconds": 3
         }
       }
     ],
diff --git a/evaluation_examples/examples/chrome/af630914-714e-4a24-a7bb-f9af687d3b91.json b/evaluation_examples/examples/chrome/af630914-714e-4a24-a7bb-f9af687d3b91.json
index 728c36f..941e98e 100644
--- a/evaluation_examples/examples/chrome/af630914-714e-4a24-a7bb-f9af687d3b91.json
+++ b/evaluation_examples/examples/chrome/af630914-714e-4a24-a7bb-f9af687d3b91.json
@@ -47,6 +47,12 @@
             "--remote-debugging-port=1337"
           ]
         }
+      },
+      {
+        "type": "sleep",
+        "parameters": {
+          "seconds": 3
+        }
       }
     ],
     "func": "check_font_size",
diff --git a/evaluation_examples/examples/chrome/bb5e4c0d-f964-439c-97b6-bdb9747de3f4.json b/evaluation_examples/examples/chrome/bb5e4c0d-f964-439c-97b6-bdb9747de3f4.json
index 91e5304..2e0d9d5 100644
--- a/evaluation_examples/examples/chrome/bb5e4c0d-f964-439c-97b6-bdb9747de3f4.json
+++ b/evaluation_examples/examples/chrome/bb5e4c0d-f964-439c-97b6-bdb9747de3f4.json
@@ -31,28 +31,11 @@
   "evaluator": {
     "postconfig": [
       {
-        "type": "execute",
-        "parameters": {
-          "command": [
-            "python3",
-            "-c",
-            "import pyautogui; pyautogui.press('f5')"
-          ]
-        }
-      },
-      {
-        "type": "sleep",
-        "parameters": {
-          "seconds": 3
-        }
-      },
-      {
-        "type": "execute",
+        "type": "launch",
         "parameters": {
           "command": [
             "pkill",
-            "-f",
-            "google-chrome"
+            "chrome"
           ]
         }
       },
@@ -65,37 +48,6 @@
           ]
         }
       },
-      {
-        "type": "launch",
-        "parameters": {
-          "command": [
-            "socat",
-            "tcp-listen:9222,fork",
-            "tcp:localhost:1337"
-          ]
-        }
-      },
-      {
-        "type": "chrome_open_tabs",
-        "parameters": {
-          "urls_to_open": [
-            "chrome://settings/search",
-            "chrome://settings"
-          ]
-        }
-      },
-      {
-        "type": "sleep",
-        "parameters": {
-          "seconds": 3
-        }
-      },
-      {
-        "type": "execute",
-        "parameters": {
-          "command": ["pkill", "-SIGHUP", "-f", "google-chrome"]
-        }
-      },
       {
         "type": "sleep",
         "parameters": {